{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:03:56Z","timestamp":1780632236508,"version":"3.54.1"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T00:00:00Z","timestamp":1772841600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T00:00:00Z","timestamp":1772841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62476196"],"award-info":[{"award-number":["62476196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-025-02715-w","type":"journal-article","created":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T08:19:37Z","timestamp":1772871577000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Video Shadow Detection with Intra-and Inter-video Cooperation"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5501-9575","authenticated-orcid":false,"given":"Liang","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junting","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,7]]},"reference":[{"issue":"4","key":"2715_CR1","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TIP.2008.916989","volume":"17","author":"C Benedek","year":"2008","unstructured":"Benedek, C., & Sziranyi, T. (2008). Bayesian foreground and shadow detection in uncertain frame rate surveillance videos. IEEE Transactions on Image Processing, 17(4), 608\u2013621.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2715_CR2","doi-asserted-by":"crossref","unstructured":"Brutzer, S., H\u00f6ferlin, B., & Heidemann, G. (2011). Evaluation of background subtraction techniques for video surveillance. In Proceedings of CVPR (pp. 1937\u20131944).","DOI":"10.1109\/CVPR.2011.5995508"},{"key":"2715_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L. C., Lopes, R., Cheng, B., Collins, M., Cubuk, E., Zoph, B., Adam, H., & Shlens, J. (2020a). Naive-student: Leveraging semi-supervised learning in video sequences for urban scene segmentation. In Proceedings of ECCV (pp. 695\u2013714).","DOI":"10.1007\/978-3-030-58545-7_40"},{"key":"2715_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Tan, X., Wang, B., & Hu, X. (2018). Reverse attention for salient object detection. In Proceedings of ECCV (pp. 234\u2013250).","DOI":"10.1007\/978-3-030-01240-3_15"},{"key":"2715_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020b). A simple framework for contrastive learning of visual representations. In Proceedings of ICML (pp. 1597\u20131607)."},{"key":"2715_CR6","unstructured":"Chen, X., Fan, H., Girshick, R., & He, K. (2020c). Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"2715_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Lu, X., Zhang, L., & Xiao, C. (2022). Semi-supervised video shadow detection via image-assisted pseudo-label generation. In Proceedings of ACMMM (pp. 2700\u20132708).","DOI":"10.1145\/3503161.3548074"},{"key":"2715_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wan, L., Zhu, L., Shen, J., Fu, H., Liu, W., & Qin, J. (2021). Triple-cooperative video shadow detection. In Proceedings of CVPR (pp. 2715\u20132724).","DOI":"10.1109\/CVPR46437.2021.00274"},{"key":"2715_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhu, L., Wan, L., Wang, S., Feng, W., & Heng, PA. (2020d). A multi-task mean teacher for semi-supervised shadow detection. In Proceedings of CVPR (pp. 5611\u20135620).","DOI":"10.1109\/CVPR42600.2020.00565"},{"issue":"10","key":"2715_CR10","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1109\/TPAMI.2003.1233909","volume":"25","author":"R Cucchiara","year":"2003","unstructured":"Cucchiara, R., Grana, C., Piccardi, M., & Prati, A. (2003). Detecting moving objects, ghosts, and shadows in video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(10), 1337\u20131342.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR11","doi-asserted-by":"crossref","unstructured":"Ding, X., Yang, J., Hu, X., & Li, X. (2022) Learning shadow correspondence for video shadow detection. In Proceedings of ECCV (pp. 705\u2013722).","DOI":"10.1007\/978-3-031-19790-1_42"},{"key":"2715_CR12","doi-asserted-by":"crossref","unstructured":"Ecins, A., Fermuller, C., & Aloimonos, Y. (2014) Shadow free segmentation in still images using local density measure. In Proceedings of ICCP (pp. 1\u20138).","DOI":"10.1109\/ICCPHOT.2014.6831803"},{"key":"2715_CR13","doi-asserted-by":"crossref","unstructured":"Fan, D., Ji, G., Zhou, T., Chen, G., Fu, H., Shen, J., & Shao, L. (2020) Pranet: Parallel reverse attention network for polyp segmentation. In Proceedings of MICCAI (pp. 263\u2013273).","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"2715_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., Ling, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, & Y., Liao, C. (2019) Lasot: A high-quality benchmark for large-scale single object tracking. In Proceedings of CVPR (pp. 5374\u20135383).","DOI":"10.1109\/CVPR.2019.00552"},{"key":"2715_CR15","doi-asserted-by":"crossref","unstructured":"Fang, X., He, X., Wang, L., & Shen, J. (2021). Robust shadow detection by exploring effective shadow contexts. In ACMMM (pp. 2927\u20132935).","DOI":"10.1145\/3474085.3475199"},{"issue":"1","key":"2715_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s11263-009-0243-z","volume":"85","author":"G Finlayson","year":"2009","unstructured":"Finlayson, G., Drew, M., & Lu, C. (2009). Entropy minimization for shadow removal. International Journal of Computer Vision, 85(1), 35\u201357.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2715_CR17","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/TPAMI.2006.18","volume":"28","author":"G Finlayson","year":"2006","unstructured":"Finlayson, G., Hordley, S., Lu, C., & Drew, M. (2006). On the removal of shadows from images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(1), 59\u201368.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR18","unstructured":"Fu, L., Guo, Q., Juefei-Xu, F., Yu, H., Feng, W., Liu, Y., & Wang, S. (2021) Benchmarking shadow removal for facial landmark detection and beyond. arXiv preprint arXiv:2111.13790"},{"key":"2715_CR19","doi-asserted-by":"crossref","unstructured":"Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., & Lucey, S. (2017) Need for speed: A benchmark for higher frame rate object tracking. In Proceedings of ICCV (pp. 1134\u20131143).","DOI":"10.1109\/ICCV.2017.128"},{"key":"2715_CR20","doi-asserted-by":"crossref","unstructured":"Graham, M., Pinaya, W. H., Tudosiu, P. D., Nachev, P., Ourselin, S., & Cardoso, M. (2022) Denoising diffusion models for out-of-distribution detection. arXiv preprint arXiv:2211.07740","DOI":"10.1109\/CVPRW59228.2023.00296"},{"key":"2715_CR21","doi-asserted-by":"crossref","unstructured":"Guo, R., Dai, Q., & Hoiem, D. (2011) Single-image shadow detection and removal using paired regions. In Proceedings of CVPR (pp. 2033\u20132040).","DOI":"10.1109\/CVPR.2011.5995725"},{"key":"2715_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) Momentum contrast for unsupervised visual representation learning. In Proceedings of CVPR.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2715_CR23","unstructured":"Horprasert, T., Harwood, D., & Davis, L. (2000). A robust background subtraction and shadow detection. In Proceedings of ACCV (pp. 983\u2013988)."},{"issue":"4","key":"2715_CR24","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/TPAMI.2018.2815688","volume":"41","author":"Q Hou","year":"2019","unstructured":"Hou, Q., Cheng, M., Hu, X., Borji, A., Tu, Z., & Torr, P. (2019). Deeply supervised salient object detection with short connections. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(4), 815\u2013828.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR25","unstructured":"Hu, S., Le, H., & Samaras, D. (2021a). Temporal feature warping for video shadow detection. arXiv preprint arXiv:2107.14287"},{"issue":"11","key":"2715_CR26","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1109\/TPAMI.2019.2919616","volume":"42","author":"X Hu","year":"2020","unstructured":"Hu, X., Fu, C. W., Zhu, L., Qin, J., & Heng, P. A. (2020). Direction-aware spatial context features for shadow detection and removal. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(11), 2795\u20132808.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR27","doi-asserted-by":"publisher","first-page":"1925","DOI":"10.1109\/TIP.2021.3049331","volume":"30","author":"X Hu","year":"2021","unstructured":"Hu, X., Wang, T., Fu, C. W., Jiang, Y., Wang, Q., & Heng, P. A. (2021). Revisiting shadow detection: A new benchmark dataset for complex world. IEEE Transactions on Image Processing, 30, 1925\u20131934.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2715_CR28","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhu, L., Fu, CW., Qin, J., & Heng, PA. (2018). Direction-aware spatial context features for shadow detection. In Proceedings of CVPR (pp. 7454\u20137462).","DOI":"10.1109\/CVPR.2018.00778"},{"key":"2715_CR29","doi-asserted-by":"crossref","unstructured":"Huang, X., Hua, G., Tumblin, J., & Williams, L. (2011). What characterizes a shadow boundary under the sun and sky? In Proceedings of ICCV (pp. 898\u2013905).","DOI":"10.1109\/ICCV.2011.6126331"},{"key":"2715_CR30","doi-asserted-by":"crossref","unstructured":"Huynh, C., Tran, A. T., Luu, K., & Hoai, M. (2021). Progressive semantic segmentation. In Proceedings of CVPR (pp. 16755\u201316764).","DOI":"10.1109\/CVPR46437.2021.01648"},{"issue":"1","key":"2715_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15701\/kcgs.2012.18.1.1","volume":"18","author":"GH Hwang","year":"2012","unstructured":"Hwang, G. H., & Park, S. H. (2012). Feature-based light and shadow estimation for video compositing and editing. Journal of the Korea Computer Graphics Society, 18(1), 1\u20139.","journal-title":"Journal of the Korea Computer Graphics Society"},{"key":"2715_CR32","doi-asserted-by":"crossref","unstructured":"Jacques, J. C. S., Jung, C. R., & Musse, S. R. (2005). Background subtraction and shadow detection in grayscale video sequences. In SIBGRAPI.","DOI":"10.1109\/SIBGRAPI.2005.15"},{"key":"2715_CR33","doi-asserted-by":"crossref","unstructured":"Junejo, I., & Foroosh, H. (2008). Estimating geo-temporal location of stationary cameras using shadow trajectories. In Proceedings of ECCV (pp. 318\u2013331).","DOI":"10.1007\/978-3-540-88682-2_25"},{"key":"2715_CR34","doi-asserted-by":"crossref","unstructured":"Karim, R., Zhao, H., Wildes, RP., & Siam, M. (2023). Med-vt: Multiscale encoder-decoder video transformer with application to object segmentation. In Proceedings of CVPR (pp. 6323\u20136333).","DOI":"10.1109\/CVPR52729.2023.00612"},{"key":"2715_CR35","doi-asserted-by":"crossref","unstructured":"Karsch, K., Hedau, V., Forsyth, D., & Hoiem, D. (2011). Rendering synthetic objects into legacy photographs. ACM Transactions on Graphics,30(6), 157:1\u2013157:12.","DOI":"10.1145\/2070781.2024191"},{"key":"2715_CR36","doi-asserted-by":"crossref","unstructured":"Khan, S. H., Bennamoun, M., Sohel, F., & Togneri, R. (2014). Automatic feature learning for robust shadow detection. In Proceedings of CVPR (pp. 1939\u20131946).","DOI":"10.1109\/CVPR.2014.249"},{"issue":"11","key":"2715_CR37","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TPAMI.2016.2516982","volume":"38","author":"M Kristan","year":"2016","unstructured":"Kristan, M., Matas, J., Leonardis, A., Vojir, T., Pflugfelder, R., Fernandez, G., Nebehay, G., Porikli, F., & Cehovin, L. (2016). A novel performance evaluation methodology for single-target trackers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(11), 2137\u20132155.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR38","doi-asserted-by":"crossref","unstructured":"Lalonde, J. F., Efros, A., & Narasimhan, S. (2009). Estimating natural illumination from a single outdoor image. In Proceedings of ICCV (pp. 183\u2013190).","DOI":"10.1109\/ICCV.2009.5459163"},{"key":"2715_CR39","doi-asserted-by":"crossref","unstructured":"Lalonde, J. F., Efros, A., & Narasimhan, S. (2010). Detecting ground shadows in outdoor consumer photographs. In Proceedings of ECCV (pp. 322\u2013335).","DOI":"10.1007\/978-3-642-15552-9_24"},{"key":"2715_CR40","doi-asserted-by":"crossref","unstructured":"Le, H., Vicente, Y., Tomas, F., Nguyen, V., Hoai, M., & Samaras, D. (2018). A+ D Net: Training a shadow detector with adversarial shadow attenuation. In Proceedings of ECCV (pp. 662\u2013678).","DOI":"10.1007\/978-3-030-01216-8_41"},{"key":"2715_CR41","doi-asserted-by":"crossref","unstructured":"Li, H., Chen, G., Li, G., & Yu, Y. (2019). Motion guided attention for video salient object detection. In Proceedings of ICCV (pp. 7274\u20137283).","DOI":"10.1109\/ICCV.2019.00737"},{"issue":"12","key":"2715_CR42","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1109\/TIP.2015.2482905","volume":"24","author":"P Liang","year":"2015","unstructured":"Liang, P., Blasch, E., & Ling, H. (2015). Encoding color information for visual tracking: Algorithms and benchmark. IEEE Transactions on Image Processing, 24(12), 5630\u20135644.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2715_CR43","doi-asserted-by":"crossref","unstructured":"Liu, L., Prost, J., Zhu, L., Papadakis, N., Li\u00f2, P., Sch\u00f6nlieb, C. B., & Aviles-Rivero, A. I. (2022). Scotch and soda: A transformer video shadow detection framework. arXiv preprint arXiv:2211.06885","DOI":"10.1109\/CVPR52729.2023.01007"},{"key":"2715_CR44","doi-asserted-by":"crossref","unstructured":"Lu, X., Cao, Y., Liu, S., Long, C., Chen, Z., Zhou, X., Yang, Y., & Xiao, C. (2022). Video shadow detection via spatio-temporal interpolation consistency training. In Proceedings of CVPR (pp. 3116\u20133125).","DOI":"10.1109\/CVPR52688.2022.00312"},{"key":"2715_CR45","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., & Porikli, F. (2019). See more, know more: Unsupervised video object segmentation with co-attention Siamese networks. In Proceedings of CVPR (pp. 3623\u20133632).","DOI":"10.1109\/CVPR.2019.00374"},{"key":"2715_CR46","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., Garcia, D., Ginsburg, B., Houston, M., Kuchaiev, O., Venkatesh, G., et\u00a0al. (2018). Mixed precision training. In ICLR."},{"issue":"8","key":"2715_CR47","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1109\/TPAMI.2004.51","volume":"26","author":"S Nadimi","year":"2004","unstructured":"Nadimi, S., & Bhanu, B. (2004). Physical models for moving shadow and object detection in video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(8), 1079\u20131087.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen, V., Vicente, T., Zhao, M., Hoai, M., & Samaras, D. (2017). Shadow detection with conditional generative adversarial networks. In Proceedings of ICCV (pp. 4510\u20134518).","DOI":"10.1109\/ICCV.2017.483"},{"key":"2715_CR49","doi-asserted-by":"crossref","unstructured":"Nilsson, D., & Sminchisescu, C. (2018). Semantic video segmentation by gated recurrent flow propagation. In Proceedings of CVPR (pp. 6819\u20136828).","DOI":"10.1109\/CVPR.2018.00713"},{"key":"2715_CR50","doi-asserted-by":"crossref","unstructured":"Okabe, T., Sato, I., & Sato, Y. (2009). Attached shadow coding: Estimating surface normals from shadows under unknown reflectance and lighting conditions. In Proceedings of ICCV (pp. 1693\u20131700).","DOI":"10.1109\/ICCV.2009.5459381"},{"issue":"7","key":"2715_CR51","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1109\/TPAMI.2003.1206520","volume":"25","author":"A Prati","year":"2003","unstructured":"Prati, A., Mikic, I., Trivedi, M., & Cucchiara, R. (2003). Detecting moving shadows: Algorithms and evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7), 918\u2013923.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR52","doi-asserted-by":"crossref","unstructured":"Song, H., Wang, W., Zhao, S., Shen, J., & Lam, KM. (2018). Pyramid dilated deeper convlstm for video salient object detection. In Proceedings of ECCV (pp. 715\u2013731).","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"2715_CR53","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.patcog.2015.09.006","volume":"51","author":"J Tian","year":"2016","unstructured":"Tian, J., Qi, X., Qu, L., & Tang, Y. (2016). New spectrum ratio properties and features for shadow detection. Pattern Recognition, 51, 85\u201396.","journal-title":"Pattern Recognition"},{"key":"2715_CR54","doi-asserted-by":"crossref","unstructured":"Vicente, T., Hou, L., Yu, C. P., Hoai, M., & Samaras, D. (2016). Large-scale training of shadow detectors with noisily-annotated shadow examples. In Proceedings of ECCV (pp. 816\u2013832).","DOI":"10.1007\/978-3-319-46466-4_49"},{"key":"2715_CR55","doi-asserted-by":"crossref","unstructured":"Vicente, Y., Tomas, F., Hoai, M., & Samaras, D. (2015). Leave-one-out kernel optimization for shadow detection. In Proceedings of ICCV (pp. 3388\u20133396).","DOI":"10.1109\/ICCV.2015.387"},{"key":"2715_CR56","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, X., & Yang, J. (2018). Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In Proceedings of CVPR (pp. 1788\u20131797).","DOI":"10.1109\/CVPR.2018.00192"},{"issue":"3","key":"2715_CR57","first-page":"3259","volume":"45","author":"T Wang","year":"2022","unstructured":"Wang, T., Hu, X., Heng, P. A., & Fu, C. W. (2022). Instance shadow detection with a single-stage detector. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3259\u20133273.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR58","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, T., Yu, F., Dai, J., Konukoglu, E., & Van\u00a0Gool, L. (2021). Exploring cross-image pixel contrast for semantic segmentation. In Proceedings of ICCV (pp. 7303\u20137313).","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"2715_CR59","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, H., Huang, W., & Scott, M. R. (2020). Cross-batch memory for embedding learning. In Proceedings of CVPR (pp. 6388\u20136397).","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"2715_CR60","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhao, X., Li, Y., Hu, X., Huang, K, et\u00a0al. (2019). Densely cascaded shadow detection network via deeply supervised parallel fusion. In Proceedings of IJCAI (pp. 1007\u20131013).","DOI":"10.24963\/ijcai.2018\/140"},{"issue":"9","key":"2715_CR61","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., & Yang, M. H. (2015). Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), 1834\u20131848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2715_CR62","doi-asserted-by":"crossref","unstructured":"Wu, Z., Su, L., & Huang, Q. (2019). Cascaded partial decoder for fast and accurate salient object detection. In Proceedings of CVPR (pp. 3907\u20133916).","DOI":"10.1109\/CVPR.2019.00403"},{"key":"2715_CR63","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, SX., & Lin, D. (2018). Unsupervised feature learning via non-parametric instance discrimination. In Proceedings of CVPR (pp. 3733\u20133742).","DOI":"10.1109\/CVPR.2018.00393"},{"key":"2715_CR64","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of CVPR (pp. 1492\u20131500).","DOI":"10.1109\/CVPR.2017.634"},{"key":"2715_CR65","doi-asserted-by":"crossref","unstructured":"Yan, P., Li, G., Xie, Y., Li, Z., Wang, C., Chen, T., & Lin, L. (2019). Semi-supervised video salient object detection using pseudo-labels. In Proceedings of ICCV (pp. 7284\u20137293).","DOI":"10.1109\/ICCV.2019.00738"},{"key":"2715_CR66","doi-asserted-by":"crossref","unstructured":"Yang, L., Fan, Y., & Xu, N. (2019). Video instance segmentation. In Proceedings of CVPR (pp. 5188\u20135197).","DOI":"10.1109\/ICCV.2019.00529"},{"key":"2715_CR67","unstructured":"YouTube. (2022). https:\/\/www.youtube.com\/"},{"key":"2715_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., & Jia, J. (2018). ICNet for real-time semantic segmentation on high-resolution images. In Proceedings of ECCV (pp. 405\u2013420).","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"2715_CR69","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1109\/TIP.2023.3348659","volume":"33","author":"X Zhao","year":"2024","unstructured":"Zhao, X., Liang, H., Li, P., Sun, G., Zhao, D., Liang, R., & He, X. (2024). Motion-aware memory network for fast video salient object detection. IEEE Transactions on Image Processing, 33, 709\u2013721.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2715_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Qiao, X., Cao, Y., & Lau, R. (2019). Distraction-aware shadow detection. In Proceedings of CVPR (pp. 5167\u20135176).","DOI":"10.1109\/CVPR.2019.00531"},{"key":"2715_CR71","doi-asserted-by":"crossref","unstructured":"Zhu, L., Deng, Z., Hu, X., Fu, CW., Xu, X., Qin, J., & Heng, P. A. (2018). Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. In Proceedings of ECCV (pp. 121\u2013136).","DOI":"10.1007\/978-3-030-01231-1_8"},{"key":"2715_CR72","doi-asserted-by":"crossref","unstructured":"Zhu, L., Xu, K., Ke, Z., & Lau, R. (2021). Mitigating intensity bias in shadow detection via feature decomposition and reweighting. In Proceedings of ICCV (pp. 4702\u20134711).","DOI":"10.1109\/ICCV48922.2021.00466"},{"key":"2715_CR73","doi-asserted-by":"crossref","unstructured":"Zhu, J., Samuel, K., Masood, S., & Tappen, M. (2010). Learning to recognize shadows in monochromatic natural images. In Proceedings of CVPR (pp. 223\u2013230).","DOI":"10.1109\/CVPR.2010.5540209"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02715-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02715-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02715-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:31:38Z","timestamp":1779348698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02715-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,7]]},"references-count":73,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2715"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02715-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,7]]},"assertion":[{"value":"21 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"166"}}